© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1291
    Prev
    Next
    INDEX
    Explanations

    duties and responsibilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '
    1.43
    auche
    1.31
    /
    1.22
    .。
    1.21
    ados
    1.19
    ,
    1.17
    -
    1.14
    ants
    1.12
    ica
    1.12
     Forced
    1.10
    POSITIVE LOGITS
    ᐟ
    2.10
     انا
    1.88
    िनेशन
    1.75
    الن
    1.74
    िडेट
    1.72
     你
    1.68
    Prevent
    1.65
    esai
    1.65
     いる
    1.64
    ÜR
    1.64
    Activations Density 0.212%

    No Known Activations